© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 3457
    Prev
    Next
    INDEX
    Explanations

    combinations of words indicating necessity or causality

    oai_token-act-pair · gpt-3.5-turbo

    constructs phrased as "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.82
    PsyNetMessage
    -0.72
     Formation
    -0.68
    oneliness
    -0.66
     Lines
    -0.65
    rones
    -0.65
    PHOTOS
    -0.65
     Doodle
    -0.63
     Noir
    -0.63
     srfAttach
    -0.63
    POSITIVE LOGITS
     worthwhile
    1.31
     successful
    1.28
     effective
    1.27
     viable
    1.25
     useful
    1.21
     profitable
    1.20
     meaningful
    1.16
     able
    1.15
     usable
    1.14
     acceptable
    1.13
    Activations Density 0.186%

    No Known Activations